Patches for rc1: nothing major, just some minor bugfixes and

code cleanups.

The following changes since commit f7e1914adad8885a5d4c70239ab90d901ed97e9f:

Merge remote-tracking branch 'remotes/alistair/tags/pull-riscv-to-apply-20201109' into staging (2020-11-10 09:24:56 +0000)

https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20201110

for you to fetch changes up to b6c56c8a9a4064ea783f352f43c5df6231a110fa:

target/arm/translate-neon.c: Handle VTBL UNDEF case before VFP access check (2020-11-10 11:03:48 +0000)

* hw/arm/Kconfig: ARM_V7M depends on PTIMER

* Minor coding style fixes

* docs: add some notes on the sbsa-ref machine

* hw/arm/virt: Remove dependency on Cortex-A15 MPCore peripherals

* target/arm: Fix neon VTBL/VTBX for len > 1

* hw/arm/armsse: Correct expansion MPC interrupt lines

* hw/misc/stm32f2xx_syscfg: Remove extraneous IRQ

* hw/arm/nseries: Remove invalid/unnecessary n8x0_uart_setup()

* hw/arm/musicpal: Don't connect two qemu_irqs directly to the same input

* hw/arm/musicpal: Only use qdev_get_gpio_in() when necessary

* hw/arm/nseries: Check return value from load_image_targphys()

* tests/qtest/npcm7xx_rng-test: count runs properly

* target/arm/translate-neon.c: Handle VTBL UNDEF case before VFP access check

Alex Bennée (1):

docs: add some notes on the sbsa-ref machine

AlexChen (1):

ssi: Fix bad printf format specifiers

Andrew Jones (1):

hw/arm/Kconfig: ARM_V7M depends on PTIMER

Havard Skinnemoen (1):

tests/qtest/npcm7xx_rng-test: count runs properly

Peter Maydell (2):

hw/arm/nseries: Check return value from load_image_targphys()

target/arm/translate-neon.c: Handle VTBL UNDEF case before VFP access check

From: Xinhao Zhang <zhangxinhao1@huawei.com>

Fix code style. Operator needs spaces both sides.

Signed-off-by: Xinhao Zhang <zhangxinhao1@huawei.com>

Signed-off-by: Kai Deng <dengkai1@huawei.com>

Message-id: 20201103114529.638233-1-zhangxinhao1@huawei.com

target/arm/arch_dump.c | 8 ++++----

target/arm/arm-semi.c | 8 ++++----

target/arm/helper.c | 2 +-

3 files changed, 9 insertions(+), 9 deletions(-)

@@ -XXX,XX +XXX,XX @@ uint32_t HELPER(usad8)(uint32_t a, uint32_t b)

uint32_t sum;

sum = do_usad(a, b);

sum += do_usad(a >> 8, b >> 8);

- sum += do_usad(a >> 16, b >>16);

+ sum += do_usad(a >> 16, b >> 16);

sum += do_usad(a >> 24, b >> 24);

return sum;

}

The helper function did not get updated when we reorganized

the vector register file for SVE. Since then, the neon dregs

are non-sequential and cannot be simply indexed.

At the same time, make the helper function operate on 64-bit

quantities so that we do not have to call it twice.

Fixes: c39c2b9043e

Reported-by: Ard Biesheuvel <ardb@kernel.org>

[PMM: use aa32_vfp_dreg() rather than opencoding]

Message-id: 20201105171126.88014-1-richard.henderson@linaro.org

target/arm/helper.h | 2 +-

target/arm/op_helper.c | 23 +++++++++--------

target/arm/translate-neon.c.inc | 44 +++++++++++----------------------

3 files changed, 29 insertions(+), 40 deletions(-)

diff --git a/target/arm/helper.h b/target/arm/helper.h

--- a/target/arm/helper.h

+++ b/target/arm/helper.h

@@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_2(rsqrte_f32, TCG_CALL_NO_RWG, f32, f32, ptr)

DEF_HELPER_FLAGS_2(rsqrte_f64, TCG_CALL_NO_RWG, f64, f64, ptr)

DEF_HELPER_FLAGS_1(recpe_u32, TCG_CALL_NO_RWG, i32, i32)

DEF_HELPER_FLAGS_1(rsqrte_u32, TCG_CALL_NO_RWG, i32, i32)

-DEF_HELPER_FLAGS_4(neon_tbl, TCG_CALL_NO_RWG, i32, i32, i32, ptr, i32)

+DEF_HELPER_FLAGS_4(neon_tbl, TCG_CALL_NO_RWG, i64, env, i32, i64, i64)

DEF_HELPER_3(shl_cc, i32, env, i32, i32)

DEF_HELPER_3(shr_cc, i32, env, i32, i32)

diff --git a/target/arm/op_helper.c b/target/arm/op_helper.c

index XXXXXXX..XXXXXXX 100644

--- a/target/arm/op_helper.c

+++ b/target/arm/op_helper.c

@@ -XXX,XX +XXX,XX @@ void raise_exception_ra(CPUARMState *env, uint32_t excp, uint32_t syndrome,

cpu_loop_exit_restore(cs, ra);

}

-uint32_t HELPER(neon_tbl)(uint32_t ireg, uint32_t def, void *vn,

- uint32_t maxindex)

+uint64_t HELPER(neon_tbl)(CPUARMState *env, uint32_t desc,

+ uint64_t ireg, uint64_t def)

- uint32_t val, shift;

- uint64_t *table = vn;

+ uint64_t tmp, val = 0;

+ uint32_t maxindex = ((desc & 3) + 1) * 8;

+ uint32_t base_reg = desc >> 2;

+ uint32_t shift, index, reg;

- val = 0;

- for (shift = 0; shift < 32; shift += 8) {

- uint32_t index = (ireg >> shift) & 0xff;

+ for (shift = 0; shift < 64; shift += 8) {

+ index = (ireg >> shift) & 0xff;

if (index < maxindex) {

- uint32_t tmp = (table[index >> 3] >> ((index & 7) << 3)) & 0xff;

- val |= tmp << shift;

+ reg = base_reg + (index >> 3);

+ tmp = *aa32_vfp_dreg(env, reg);

+ tmp = ((tmp >> ((index & 7) << 3)) & 0xff) << shift;

} else {

- val |= def & (0xff << shift);

+ tmp = def & (0xffull << shift);

}

+ val |= tmp;

}

return val;

}

diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc

index XXXXXXX..XXXXXXX 100644

--- a/target/arm/translate-neon.c.inc

+++ b/target/arm/translate-neon.c.inc

@@ -XXX,XX +XXX,XX @@ static bool trans_VEXT(DisasContext *s, arg_VEXT *a)

static bool trans_VTBL(DisasContext *s, arg_VTBL *a)

{

- int n;

- TCGv_i32 tmp, tmp2, tmp3, tmp4;

- TCGv_ptr ptr1;

+ TCGv_i64 val, def;

+ TCGv_i32 desc;

if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {

return false;

@@ -XXX,XX +XXX,XX @@ static bool trans_VTBL(DisasContext *s, arg_VTBL *a)

return true;

}

- n = a->len + 1;

- if ((a->vn + n) > 32) {

+ if ((a->vn + a->len + 1) > 32) {

/*

* This is UNPREDICTABLE; we choose to UNDEF to avoid the

* helper function running off the end of the register file.

*/

return false;

}

- n <<= 3;

- tmp = tcg_temp_new_i32();

- if (a->op) {

- read_neon_element32(tmp, a->vd, 0, MO_32);

- } else {

- tcg_gen_movi_i32(tmp, 0);

- }

- tmp2 = tcg_temp_new_i32();

- read_neon_element32(tmp2, a->vm, 0, MO_32);

- ptr1 = vfp_reg_ptr(true, a->vn);

- tmp4 = tcg_const_i32(n);

- gen_helper_neon_tbl(tmp2, tmp2, tmp, ptr1, tmp4);

+ desc = tcg_const_i32((a->vn << 2) | a->len);

+ def = tcg_temp_new_i64();

if (a->op) {

- read_neon_element32(tmp, a->vd, 1, MO_32);

+ read_neon_element64(def, a->vd, 0, MO_64);

} else {

- tcg_gen_movi_i32(tmp, 0);

+ tcg_gen_movi_i64(def, 0);

}

- tmp3 = tcg_temp_new_i32();

- read_neon_element32(tmp3, a->vm, 1, MO_32);

- gen_helper_neon_tbl(tmp3, tmp3, tmp, ptr1, tmp4);

- tcg_temp_free_i32(tmp);

- tcg_temp_free_i32(tmp4);

- tcg_temp_free_ptr(ptr1);

+ val = tcg_temp_new_i64();

+ read_neon_element64(val, a->vm, 0, MO_64);

- write_neon_element32(tmp2, a->vd, 0, MO_32);

- write_neon_element32(tmp3, a->vd, 1, MO_32);

- tcg_temp_free_i32(tmp2);

- tcg_temp_free_i32(tmp3);

+ gen_helper_neon_tbl(val, cpu_env, desc, val, def);

+ write_neon_element64(val, a->vd, 0, MO_64);

+ tcg_temp_free_i64(def);

+ tcg_temp_free_i64(val);

+ tcg_temp_free_i32(desc);

return true;

}

From: Philippe Mathieu-Daudé <f4bug@amsat.org>

omap2420_mpu_init() introduced in commit 827df9f3c5f ("Add basic

OMAP2 chip support") takes care of creating the 3 UARTs.

Then commit 58a26b477e9 ("Emulate a serial bluetooth HCI with H4+

extensions and attach to n8x0's UART") added n8x0_uart_setup()

which create the UART and connects it to an IRQ output,

overwritting the existing peripheral and its IRQ connection.

This is incorrect.

Fortunately we don't need to fix this, because commit 6da68df7f9b

("hw/arm/nseries: Replace the bluetooth chardev with a "null"

chardev") removed the use of this peripheral. We can simply

remove the code.

Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>

Message-id: 20201107193403.436146-4-f4bug@amsat.org

hw/arm/nseries.c | 11 -----------

1 file changed, 11 deletions(-)

diff --git a/hw/arm/nseries.c b/hw/arm/nseries.c

--- a/hw/arm/nseries.c

+++ b/hw/arm/nseries.c

@@ -XXX,XX +XXX,XX @@ static void n8x0_cbus_setup(struct n800_s *s)

cbus_attach(cbus, s->tahvo = tahvo_init(tahvo_irq, 1));

}

-static void n8x0_uart_setup(struct n800_s *s)

-{

- Chardev *radio = qemu_chr_new("bt-dummy-uart", "null", NULL);

- /*

- * Note: We used to connect N8X0_BT_RESET_GPIO and N8X0_BT_WKUP_GPIO

- * here, but this code has been removed with the bluetooth backend.

- */

- omap_uart_attach(s->mpu->uart[BT_UART], radio);

-}

-

static void n8x0_usb_setup(struct n800_s *s)

{

SysBusDevice *dev;

@@ -XXX,XX +XXX,XX @@ static void n8x0_init(MachineState *machine,

n8x0_spi_setup(s);

n8x0_dss_setup(s);

n8x0_cbus_setup(s);

- n8x0_uart_setup(s);

if (machine_usb(machine)) {

n8x0_usb_setup(s);

}

From: Philippe Mathieu-Daudé <f4bug@amsat.org>

The MusicPal board code connects both of the IRQ outputs of the UART

to the same INTC qemu_irq. Connecting two qemu_irqs outputs directly

to the same input is not valid as it produces subtly wrong behaviour

(for instance if both the IRQ lines are high, and then one goes

low, the INTC input will see this as a high-to-low transition

even though the second IRQ line should still be holding it high).

This kind of wiring needs an explicitly created OR gate; add one.

Inspired-by: Peter Maydell <peter.maydell@linaro.org>

Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>

Message-id: 20201107193403.436146-5-f4bug@amsat.org

hw/arm/musicpal.c | 17 +++++++++++++----

hw/arm/Kconfig | 1 +

2 files changed, 14 insertions(+), 4 deletions(-)

diff --git a/hw/arm/musicpal.c b/hw/arm/musicpal.c

--- a/hw/arm/musicpal.c

+++ b/hw/arm/musicpal.c

@@ -XXX,XX +XXX,XX @@

#include "ui/console.h"

#include "hw/i2c/i2c.h"

#include "hw/irq.h"

+#include "hw/or-irq.h"

#include "hw/audio/wm8750.h"

#include "sysemu/block-backend.h"

#include "sysemu/runstate.h"

@@ -XXX,XX +XXX,XX @@

#define MP_TIMER4_IRQ 7

#define MP_EHCI_IRQ 8

#define MP_ETH_IRQ 9

-#define MP_UART1_IRQ 11

-#define MP_UART2_IRQ 11

+#define MP_UART_SHARED_IRQ 11

#define MP_GPIO_IRQ 12

#define MP_RTC_IRQ 28

#define MP_AUDIO_IRQ 30

@@ -XXX,XX +XXX,XX @@ static void musicpal_init(MachineState *machine)

ARMCPU *cpu;

qemu_irq pic[32];

DeviceState *dev;

+ DeviceState *uart_orgate;

DeviceState *i2c_dev;

DeviceState *lcd_dev;

DeviceState *key_dev;

@@ -XXX,XX +XXX,XX @@ static void musicpal_init(MachineState *machine)

pic[MP_TIMER2_IRQ], pic[MP_TIMER3_IRQ],

pic[MP_TIMER4_IRQ], NULL);

- serial_mm_init(address_space_mem, MP_UART1_BASE, 2, pic[MP_UART1_IRQ],

+ /* Logically OR both UART IRQs together */

+ uart_orgate = DEVICE(object_new(TYPE_OR_IRQ));

+ object_property_set_int(OBJECT(uart_orgate), "num-lines", 2, &error_fatal);

+ qdev_realize_and_unref(uart_orgate, NULL, &error_fatal);

+ qdev_connect_gpio_out(DEVICE(uart_orgate), 0, pic[MP_UART_SHARED_IRQ]);

+

+ serial_mm_init(address_space_mem, MP_UART1_BASE, 2,

+ qdev_get_gpio_in(uart_orgate, 0),

1825000, serial_hd(0), DEVICE_NATIVE_ENDIAN);

- serial_mm_init(address_space_mem, MP_UART2_BASE, 2, pic[MP_UART2_IRQ],

+ serial_mm_init(address_space_mem, MP_UART2_BASE, 2,

+ qdev_get_gpio_in(uart_orgate, 1),

1825000, serial_hd(1), DEVICE_NATIVE_ENDIAN);

/* Register flash */

diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig

index XXXXXXX..XXXXXXX 100644

--- a/hw/arm/Kconfig

+++ b/hw/arm/Kconfig

@@ -XXX,XX +XXX,XX @@ config MUSCA

config MUSICPAL

bool

+ select OR_IRQ

select BITBANG_I2C

select MARVELL_88W8618

select PTIMER

We don't need to fill the full pic[] array if we only use

few of the interrupt lines. Directly call qdev_get_gpio_in()

when necessary.

hw/arm/musicpal.c | 25 +++++++++++++------------

1 file changed, 13 insertions(+), 12 deletions(-)

diff --git a/hw/arm/musicpal.c b/hw/arm/musicpal.c

--- a/hw/arm/musicpal.c

+++ b/hw/arm/musicpal.c

@@ -XXX,XX +XXX,XX @@ static struct arm_boot_info musicpal_binfo = {

static void musicpal_init(MachineState *machine)

{

ARMCPU *cpu;

- qemu_irq pic[32];

DeviceState *dev;

+ DeviceState *pic;

DeviceState *uart_orgate;

DeviceState *i2c_dev;

DeviceState *lcd_dev;

@@ -XXX,XX +XXX,XX @@ static void musicpal_init(MachineState *machine)

&error_fatal);

memory_region_add_subregion(address_space_mem, MP_SRAM_BASE, sram);

- dev = sysbus_create_simple(TYPE_MV88W8618_PIC, MP_PIC_BASE,

+ pic = sysbus_create_simple(TYPE_MV88W8618_PIC, MP_PIC_BASE,

qdev_get_gpio_in(DEVICE(cpu), ARM_CPU_IRQ));

- for (i = 0; i < 32; i++) {

- pic[i] = qdev_get_gpio_in(dev, i);

- }

- sysbus_create_varargs(TYPE_MV88W8618_PIT, MP_PIT_BASE, pic[MP_TIMER1_IRQ],

- pic[MP_TIMER2_IRQ], pic[MP_TIMER3_IRQ],

- pic[MP_TIMER4_IRQ], NULL);

+ sysbus_create_varargs(TYPE_MV88W8618_PIT, MP_PIT_BASE,

+ qdev_get_gpio_in(pic, MP_TIMER1_IRQ),

+ qdev_get_gpio_in(pic, MP_TIMER2_IRQ),

+ qdev_get_gpio_in(pic, MP_TIMER3_IRQ),

+ qdev_get_gpio_in(pic, MP_TIMER4_IRQ), NULL);

/* Logically OR both UART IRQs together */

uart_orgate = DEVICE(object_new(TYPE_OR_IRQ));

object_property_set_int(OBJECT(uart_orgate), "num-lines", 2, &error_fatal);

qdev_realize_and_unref(uart_orgate, NULL, &error_fatal);

- qdev_connect_gpio_out(DEVICE(uart_orgate), 0, pic[MP_UART_SHARED_IRQ]);

+ qdev_connect_gpio_out(DEVICE(uart_orgate), 0,

+ qdev_get_gpio_in(pic, MP_UART_SHARED_IRQ));

serial_mm_init(address_space_mem, MP_UART1_BASE, 2,

qdev_get_gpio_in(uart_orgate, 0),

@@ -XXX,XX +XXX,XX @@ static void musicpal_init(MachineState *machine)

OBJECT(get_system_memory()), &error_fatal);

sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal);

sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, MP_ETH_BASE);

- sysbus_connect_irq(SYS_BUS_DEVICE(dev), 0, pic[MP_ETH_IRQ]);

+ sysbus_connect_irq(SYS_BUS_DEVICE(dev), 0,

+ qdev_get_gpio_in(pic, MP_ETH_IRQ));

sysbus_create_simple("mv88w8618_wlan", MP_WLAN_BASE, NULL);

sysbus_create_simple(TYPE_MUSICPAL_MISC, MP_MISC_BASE, NULL);

dev = sysbus_create_simple(TYPE_MUSICPAL_GPIO, MP_GPIO_BASE,

- pic[MP_GPIO_IRQ]);

+ qdev_get_gpio_in(pic, MP_GPIO_IRQ));

i2c_dev = sysbus_create_simple("gpio_i2c", -1, NULL);

i2c = (I2CBus *)qdev_get_child_bus(i2c_dev, "i2c");

@@ -XXX,XX +XXX,XX @@ static void musicpal_init(MachineState *machine)

NULL);

sysbus_realize_and_unref(s, &error_fatal);

sysbus_mmio_map(s, 0, MP_AUDIO_BASE);

- sysbus_connect_irq(s, 0, pic[MP_AUDIO_IRQ]);

+ sysbus_connect_irq(s, 0, qdev_get_gpio_in(pic, MP_AUDIO_IRQ));

musicpal_binfo.ram_size = MP_RAM_DEFAULT_SIZE;

arm_load_kernel(cpu, machine, &musicpal_binfo);

From: Havard Skinnemoen <hskinnemoen@google.com>

The number of runs is equal to the number of 0-1 and 1-0 transitions,

plus one. Currently, it's counting the number of times these transitions

do _not_ happen, plus one.

Source:

https://nvlpubs.nist.gov/nistpubs/Legacy/SP/nistspecialpublication800-22r1a.pdf

section 2.3.4 point (3).

Signed-off-by: Havard Skinnemoen <hskinnemoen@google.com>

Message-id: 20201103011457.2959989-2-hskinnemoen@google.com

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>

tests/qtest/npcm7xx_rng-test.c | 2 +-

1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tests/qtest/npcm7xx_rng-test.c b/tests/qtest/npcm7xx_rng-test.c

--- a/tests/qtest/npcm7xx_rng-test.c

+++ b/tests/qtest/npcm7xx_rng-test.c

@@ -XXX,XX +XXX,XX @@ static double calc_runs_p(const unsigned long *buf, unsigned int nr_bits)

pi = (double)nr_ones / nr_bits;

for (k = 0; k < nr_bits - 1; k++) {

- vn_obs += !(test_bit(k, buf) ^ test_bit(k + 1, buf));

+ vn_obs += (test_bit(k, buf) ^ test_bit(k + 1, buf));

}

vn_obs += 1;

Checks for UNDEF cases should go before the "is VFP enabled?" access

check, except in special cases. Move a stray UNDEF check in the VTBL

trans function up above the access check.

target/arm/translate-neon.c.inc | 8 ++++----

1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc

--- a/target/arm/translate-neon.c.inc

+++ b/target/arm/translate-neon.c.inc

@@ -XXX,XX +XXX,XX @@ static bool trans_VTBL(DisasContext *s, arg_VTBL *a)

return false;

}

- if (!vfp_access_check(s)) {

- return true;

- }

-

if ((a->vn + a->len + 1) > 32) {

/*

* This is UNPREDICTABLE; we choose to UNDEF to avoid the

@@ -XXX,XX +XXX,XX @@ static bool trans_VTBL(DisasContext *s, arg_VTBL *a)

return false;

}

+ if (!vfp_access_check(s)) {

+ return true;

+ }

desc = tcg_const_i32((a->vn << 2) | a->len);

def = tcg_temp_new_i64();

if (a->op) {